| { |
| "best_metric": 0.50592440366745, |
| "best_model_checkpoint": "/content/My Drive/LLaMA-LoRA Tuner/lora_models/earthshine-nondecorative-2023-06-27-17-40-07/checkpoint-1000", |
| "epoch": 2.808988764044944, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03, |
| "learning_rate": 2.3999999999999997e-05, |
| "loss": 2.0693, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 5.399999999999999e-05, |
| "loss": 1.9946, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 8.1e-05, |
| "loss": 1.8837, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00011099999999999999, |
| "loss": 1.6655, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00014099999999999998, |
| "loss": 1.6095, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00017099999999999998, |
| "loss": 1.3838, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.000201, |
| "loss": 1.3548, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00023099999999999998, |
| "loss": 1.0789, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.000261, |
| "loss": 1.0589, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.00029099999999999997, |
| "loss": 1.0259, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.000299393063583815, |
| "loss": 0.9936, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.0002985260115606936, |
| "loss": 0.9633, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00029765895953757224, |
| "loss": 1.0018, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002967919075144509, |
| "loss": 0.893, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00029592485549132945, |
| "loss": 0.8079, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002950578034682081, |
| "loss": 0.8668, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00029419075144508666, |
| "loss": 0.773, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.0002933236994219653, |
| "loss": 0.8139, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.0002924566473988439, |
| "loss": 0.9139, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002915895953757225, |
| "loss": 0.7371, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.0002907225433526011, |
| "loss": 0.8604, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002898554913294797, |
| "loss": 0.8597, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002889884393063584, |
| "loss": 0.7954, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00028812138728323696, |
| "loss": 0.7559, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.0002872543352601156, |
| "loss": 0.8488, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00028638728323699417, |
| "loss": 0.7252, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.0002855202312138728, |
| "loss": 0.6751, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00028465317919075143, |
| "loss": 0.7852, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.00028378612716763, |
| "loss": 0.7843, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00028291907514450864, |
| "loss": 0.7886, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00028205202312138727, |
| "loss": 0.7218, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0002811849710982659, |
| "loss": 0.7919, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.0002803179190751445, |
| "loss": 0.7248, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.0002794508670520231, |
| "loss": 0.7699, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00027858381502890174, |
| "loss": 0.6909, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.0002777167630057803, |
| "loss": 0.6992, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00027684971098265894, |
| "loss": 0.6747, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.0002759826589595375, |
| "loss": 0.672, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.0002751156069364162, |
| "loss": 0.5997, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002742485549132948, |
| "loss": 0.747, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.0002733815028901734, |
| "loss": 0.7217, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.000272514450867052, |
| "loss": 0.683, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0002716473988439306, |
| "loss": 0.63, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00027078034682080925, |
| "loss": 0.6889, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.0002699132947976878, |
| "loss": 0.6582, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00026904624277456645, |
| "loss": 0.6366, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00026817919075144503, |
| "loss": 0.7249, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.0002673121387283237, |
| "loss": 0.53, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.0002664450867052023, |
| "loss": 0.6172, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.0002655780346820809, |
| "loss": 0.6033, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.4, |
| "eval_loss": 0.5882205367088318, |
| "eval_runtime": 14.2208, |
| "eval_samples_per_second": 3.516, |
| "eval_steps_per_second": 0.492, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.0002647109826589595, |
| "loss": 0.7452, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00026384393063583813, |
| "loss": 0.6689, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.00026297687861271676, |
| "loss": 0.6339, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.00026210982658959533, |
| "loss": 0.6538, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00026124277456647397, |
| "loss": 0.6864, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.0002603757225433526, |
| "loss": 0.6466, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.00025950867052023117, |
| "loss": 0.6186, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.0002586416184971098, |
| "loss": 0.6872, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00025777456647398843, |
| "loss": 0.7206, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.000256907514450867, |
| "loss": 0.5848, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 0.00025604046242774564, |
| "loss": 0.711, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.00025517341040462427, |
| "loss": 0.628, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.00025430635838150285, |
| "loss": 0.7035, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.0002534393063583815, |
| "loss": 0.5965, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 0.0002525722543352601, |
| "loss": 0.6486, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.0002517052023121387, |
| "loss": 0.6264, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.0002508381502890173, |
| "loss": 0.6469, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00024997109826589595, |
| "loss": 0.61, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 0.0002491040462427746, |
| "loss": 0.6664, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 0.00024823699421965315, |
| "loss": 0.5312, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.0002473699421965318, |
| "loss": 0.4703, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.00024650289017341036, |
| "loss": 0.535, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 0.000245635838150289, |
| "loss": 0.6568, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 0.0002447687861271676, |
| "loss": 0.6303, |
| "step": 740 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 0.00024390173410404622, |
| "loss": 0.4911, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 0.00024303468208092483, |
| "loss": 0.5043, |
| "step": 760 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 0.00024216763005780346, |
| "loss": 0.5248, |
| "step": 770 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 0.00024130057803468206, |
| "loss": 0.6274, |
| "step": 780 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 0.00024043352601156066, |
| "loss": 0.5617, |
| "step": 790 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 0.00023956647398843927, |
| "loss": 0.5978, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 0.00023869942196531787, |
| "loss": 0.6027, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 0.00023783236994219653, |
| "loss": 0.5925, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 0.00023696531791907513, |
| "loss": 0.593, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 0.00023609826589595373, |
| "loss": 0.6181, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 0.00023523121387283234, |
| "loss": 0.4752, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 0.00023436416184971097, |
| "loss": 0.655, |
| "step": 860 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 0.00023349710982658957, |
| "loss": 0.5577, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 0.00023263005780346818, |
| "loss": 0.6132, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 0.00023176300578034678, |
| "loss": 0.5003, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 0.00023089595375722544, |
| "loss": 0.5323, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 0.00023002890173410404, |
| "loss": 0.5908, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 0.00022916184971098264, |
| "loss": 0.5911, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 0.00022829479768786125, |
| "loss": 0.565, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 0.00022742774566473988, |
| "loss": 0.5789, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.00022656069364161848, |
| "loss": 0.5242, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 0.00022569364161849708, |
| "loss": 0.5082, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 0.0002248265895953757, |
| "loss": 0.5184, |
| "step": 970 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 0.0002239595375722543, |
| "loss": 0.6131, |
| "step": 980 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 0.00022309248554913295, |
| "loss": 0.5129, |
| "step": 990 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 0.00022222543352601155, |
| "loss": 0.6016, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.81, |
| "eval_loss": 0.50592440366745, |
| "eval_runtime": 14.2225, |
| "eval_samples_per_second": 3.516, |
| "eval_steps_per_second": 0.492, |
| "step": 1000 |
| } |
| ], |
| "max_steps": 3560, |
| "num_train_epochs": 10, |
| "total_flos": 2.1070675154141184e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
